Holy 💩! Bonsai-2! My go-to iPhone model family just got a huge update and ...

This is a dev post classified by Jev as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.

Holy 💩! Bonsai-2! My go-to iPhone model family just got a huge update and ... @PrismML squeezed my favorite Qwen3.8-27B into just 5.9GB… without apparently destroying its intelligence. They released Ternary Bonsai 2 27B. Here’s the crazy comparison from their benchmarks 👇 🧠 Qwen3.8-27B FP16 💾 54GB 📊 86.32 🎯 Qwen3.8-27B UD-Q4_K_XL 💾 17.6GB 📊 85.18 🌳 Bonsai 2 27B — ~1.7 bits/weight 💾 5.9GB 👈 👀 📊 84.78 Read that again. The 5.9GB version lands just 0.4 benchmark points behind the 17.6GB Q4 while taking roughly 1/3 the space. 😳 PrismML says it retains 98.2% of the FP16 benchmark average. And

Posted by David Hendrickson (11.1k followers) 1 days ago · 79 likes · 11.1k views · view the original post on X. Kept by the Dev Radar as Other.

More dev work like this

• We’ve evaluated NVIDIA GR00T N1.7 on VLA-Replica! Check out Alex @alexhuang1029's post… — @YuXiang_IRVL
• You can run locally Uncensored Ternary Bonsai 2-27B Same 5.9GB file. — @0x0SojalSec
• dear rtx 3060 owners, and every 12gb card behind it. bonsai 2 27b dense went from 26 to… — @sudoingX
• Nice: banked codex reset for all of us. — @kimmonismus
• Nvidia dropped an official DeepSeek-V4.1-Flash NVFP4 build. — @TeksEdge
• Convolutional Neural Networks. #BigData #Analytics #DataScience #AI #MachineLearning… — @gp_pulipaka
• Reinforcement Learning and Optimal Control! #BigData #Analytics #DataScience #AI… — @gp_pulipaka
• The #Mathematical #Programming - #FPGA. #BigData #Analytics #DataScience #AI… — @gp_pulipaka

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 15.1k posts from 4.7k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 22:52 UTC. Full method.